Improvement and Application of Generative Adversarial Networks Algorithm Based on Transfer Learning

Fangming Bi,Xuanyi Fu,Wenjia Yang,Zijian Man,Yang Xia,Wei Liu,Lei Gao

doi:10.1155/2020/9453586

Fangming Bi, Xuanyi Fu + Show 5 more

Open Access

https://doi.org/10.1155/2020/9453586

Copy DOI

Abstract

Generative adversarial networks are currently used to solve various problems and are one of the most popular models. Generator and discriminator are characteristics of continuous game process in training. While improving the quality of generated pictures, it will also make it difficult for the loss function to be stable, and the training speed will be extremely slow compared with other methods. In addition, since the generative adversarial networks directly learns the data distribution of samples, the model will become uncontrollable and the freedom of the model will become too large when the original data distribution is constantly approximated. A new transfer learning training idea for the unsupervised generation model is proposed based on the generation network. The decoder of trained variational autoencoders is used as the network architecture and parameters to generative adversarial network generator. In addition, the standard normal distribution is obtained by sampling and then input into the model to control the degree of freedom of the model. Finally, we evaluated our method on using the MNIST, CIFAR10, and LSUN datasets. The experiment shows that our proposed method can make the loss function converge as quickly as possible and increase the model accuracy.

Highlights

generative adversarial networks (GANs) is a new image-generating model based on game theory, which innovatively combines the generative model and adversarial model, and proposes a useful training method based on model features to make the output resulting images clearer and sharper than other methods
The purpose of our study is speeding up model training and reducing model freedom
In all unsupervised generative models, the generation of adversarial network has the advantages of clearer and sharper image generation, and does not need to use Markov chain to sample the input dataset repeatedly, and the model is more concise than other unsupervised network models

Summary

Introduction

Compared with the previous complex image generation methods, the generation of adversarial network does not need to model its original dataset, but only needs to use generators to approach the original data distribution. Its generator and discriminator do not need complex network structure, and the original deep neural network can achieve better generation effect. Researchers have made a lot of improvements to the generation of adversarial network, there are still some points that need to be improved based on its own characteristics. The model training speed is slow and the model freedom is too large. The purpose of our study is speeding up model training and reducing model freedom

Objectives

Methods

Conclusion